Variable Importance in Matched Case Control Studies in Settings of High-Dimensional Data

• Activity Number: 628
• Type: Topic Contributed
• Date/Time: Thursday, August 8, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Raji Balasubramanian*+ and E. Andres Houseman and Brent A. Coull and Michael Lev and Lee Schwamm and Rebecca A. Betensky
• Companies: Division of Biostatistics and Epidemiology and College of Public Health and Human Sciences, Oregon State University and Harvard School of Public Health and Massachusetts General Hospital and Massachusetts General Hospital and Harvard School of Public Health
• Keywords: matching ; variable importance ; high dimensional data

Abstract

We present a method for assessing variable importance in matched case-control investigations and other highly stratified studies characterized by high dimensional data (p >> n). The proposed methods are motivated by a cardiovascular disease systems biology study involved matched cases and controls. In simulated and real datasets, we show that the proposed algorithm performs better than a conventional univariate method (conditional logistic regression) and a popular multivariable algorithm (Random Forests) that does not take the matching into account.